© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65769
    Prev
    Next
    INDEX
    Explanations

    Foundation licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -1.44
     用品
    -1.36
    satunya
    -1.34
     onun
    -1.26
    CHREIB
    -1.25
    ֽ
    -1.23
     maakt
    -1.23
     and
    -1.22
     kuni
    -1.22
    </h3>
    -1.21
    POSITIVE LOGITS
     hauptsächlich
    1.36
     vorbere
    1.35
    几分
    1.33
     Inadequate
    1.32
    是因為
    1.25
    Fär
    1.24
    -
    1.24
     maî
    1.24
     niên
    1.23
     üblichen
    1.23
    Activations Density 0.000%

    No Known Activations